Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3141 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.9409. Min Act: -0.1700
Data Index: 8146678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.9409. Min Act: -0.1700
Data Index: 8752384 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.9096. Min Act: -0.1700
Data Index: 4906955 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8784. Min Act: -0.1700
Data Index: 122467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8471. Min Act: -0.1700
Data Index: 2580362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8471. Min Act: -0.1700
Data Index: 293558 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8471. Min Act: -0.1700
Data Index: 6299723 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8471. Min Act: -0.1700
Data Index: 393722 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8471. Min Act: -0.1700
Data Index: 4071737 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 8636964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 1473950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 49672 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 4354374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 2154975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 2269686 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 4377225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 4534980 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 4937012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 4064858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8158. Min Act: -0.1700
Data Index: 7078664 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19